# /// script
# requires-python = ">=3.10"
# dependencies = [
#     "transformers",
#     "peft",
#     "accelerate",
#     "safetensors",
#     "huggingface_hub"
# ]
# ///
from transformers import AutoModelForCausalLM, AutoTokenizer
from peft import PeftModel
import torch

base_model = "Qwen/Qwen2.5-7B-Instruct"
lora_model = "daemongg/qwen2.5-7b-sre-grpo"
output_repo = "Yaswanth-Bolla/qwen-merged"

tokenizer = AutoTokenizer.from_pretrained(base_model)

model = AutoModelForCausalLM.from_pretrained(
    base_model,
    torch_dtype=torch.float16,
    device_map="auto"
)

model = PeftModel.from_pretrained(model, lora_model)

model = model.merge_and_unload()

model.push_to_hub(output_repo)
tokenizer.push_to_hub(output_repo)